Prerequisites
Node.js 18+ (or Python 3.10+) and an Agentomy account. Nothing else to install on your infrastructure.
Docs / Deploy the Agent
Add governance to your AI agent in a few minutes.
Sign up, generate a key, connect the agent, and watch governed actions show up in your audit trail.
Create your account
Sign up and confirm your email. Your workspace is created the moment you finish.
Generate an API key
In the dashboard, open API Keys and generate one. Copy it once: it is shown a single time. You can rotate or revoke it anytime.
Install the agent
Add the open Agentomy agent to your project. It is free; the governance platform behind it is the commercial product.
Connect it
Set your API key as an environment variable and point the agent at your Agentomy endpoint (or drop in the MCP config for Claude Code / Cursor).
Verify
Make one governed call. You get back an authorization decision and an audit id, and you can see the event appear in your dashboard.
Step 3, in detail
Generating your API key
Dashboard → API Keys → Generate. Copy the key immediately: it is displayed once. Scope it to the tier you need, and rotate or revoke whenever you want.
Dashboard / API KeysSample not a live key
Your Agentomy API key
Authenticates your agent to the Agentomy governance server. Put it in the agentomy-agent MCP plugin alongside your own model keys, which stay in your environment.
agentomy-agent MCP config
{
"mcpServers": {
"agentomy-agent": {
"command": "npx",
"args": ["-y", "agentomy-mcp-gateway", "--", "<your-mcp-server-command>"],
"env": {
"AGENTOMY_API_KEY": "<your-agentomy-api-key>",
"AGENTOMY_ENDPOINT": "https://api.agentomy.com"
}
}
}
}The control plane stores only a hash and a masked hint — never the key itself.